Picture for Jan Hązła

Jan Hązła

An initial alignment between neural network and target is needed for gradient descent to learn

Add code
Feb 25, 2022
Figure 1 for An initial alignment between neural network and target is needed for gradient descent to learn
Figure 2 for An initial alignment between neural network and target is needed for gradient descent to learn
Viaarxiv icon

A Johnson--Lindenstrauss Framework for Randomly Initialized CNNs

Add code
Nov 03, 2021
Figure 1 for A Johnson--Lindenstrauss Framework for Randomly Initialized CNNs
Figure 2 for A Johnson--Lindenstrauss Framework for Randomly Initialized CNNs
Viaarxiv icon

Regularization by Misclassification in ReLU Neural Networks

Add code
Nov 03, 2021
Figure 1 for Regularization by Misclassification in ReLU Neural Networks
Figure 2 for Regularization by Misclassification in ReLU Neural Networks
Figure 3 for Regularization by Misclassification in ReLU Neural Networks
Figure 4 for Regularization by Misclassification in ReLU Neural Networks
Viaarxiv icon

Bayesian Decision Making in Groups is Hard

Add code
Jul 14, 2018
Figure 1 for Bayesian Decision Making in Groups is Hard
Figure 2 for Bayesian Decision Making in Groups is Hard
Figure 3 for Bayesian Decision Making in Groups is Hard
Figure 4 for Bayesian Decision Making in Groups is Hard
Viaarxiv icon